Claim Missing Document
Check
Articles

MODEL JARINGAN SYARAF TIRUAN DALAM MEMPREDIKSI EKSISTENSI PROGRAM STUDI KOMPUTERISASI AKUNTANSI (STUDI KASUS : AMIK TUNAS BANGSA PEMATANGSIANTAR) Ilham, Muhammad; Lubis, Ega Khairunnisa; Aisyah, Nurfahana Siti; Lubis, Muhammad Ridwan; Solikhun, Solikhun
Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol 10, No 1 (2019): JURNAL SIMETRIS VOLUME 10 NO 1 TAHUN 2019
Publisher : Fakultas Teknik Universitas Muria Kudus

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24176/simet.v10i1.3031

Abstract

Program studi Komputerisasi Akuntansi adalah program studi yang mempelajari tentang sistem akuntansi dimana komputer sebagai teknologi untuk menjalankan aplikasi untuk mengolah data transaksi akuntansi dan sekaligus untuk menghasilkan laporan akuntansi. Arah kajian keilmuan dari program studi ini mencakup disiplin, proses, teknik dan alat bantu yang dibutuhkan dalam rekayasa sistem informasi akuntansi yang meliputi tahap perencanaan, pembangunan, implementasi dan pemeliharaan. Komputerisasi Akuntansi banyak dibutuhkan di hampir semua bidang dunia kerja, terutama dalam menghadapi era globalisasi yang tak terlepas dari dunia teknologi dan informasi, sehingga perlu dipersiapkan sumber daya manusia yang memiliki kualitas untuk berkompetisi dalam setiap aspek khusunya bidang komputerisasi akuntansi. Tujuan prediksi ini untuk mengetahui, apakah program studi komputerisasi akuntansi masih diminati oleh mahasiswa atau tidak sampai 10 tahun kedepan. Prediksi eksistensi ini menggunakan metode jaringan syaraf tiruan backpropagation. Jaringan syaraf tiruan (JST) adalah paradigm pemrosesan suatu informasi yang terinspirasi oleh sistem sel syaraf biologi. Jaringan ini biasanya diimplementasikan dengan menggunakan komponen elektronik atau disimulasikan pada aplikasi computer. Variabel masukan (input) yang digunakan adalah data tahun 2010 sampai 2017 dengan model arsitektur pelatihan dan pengujian sebanyak 4 arsitektur yakni 8-4-1, 8-6-1, 8-8-1 dan 8-10-1. Data target diambil dari data tahun 2018. Keluaran yang dihasilkan adalah pola terbaik dari arsitektur JST. Model arsitektur terbaik adalah 8-4-1 dengan epoch 3449, MSE 0,02495690 dan tingkat akurasi 67%. Dari model ini maka dihasilkan prediksi Eksistensi Program Studi Komputerisasi Akuntansi di AMIK Tunas Bangsa.
RETRACTED : Decision support system in Predicting the Best teacher with Multi Atribute Decesion Making Weighted Product (MADMWP) Method Solikhun, Solikhun; Windarto, Agus Perdana; Amri, Amri
International Journal of Artificial Intelligence Research Vol 1, No 1 (2017): June 2017
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (124.218 KB) | DOI: 10.29099/ijair.v1i1.1

Abstract

Following a rigorous, carefully concerns and considered review of the article published in International Journal of Artificial Intelligence Research to article entitled “Decision support system in Predicting the Best teacher with Multi-Attribute Decision Making Weighted Product (MADMWP) Method” Vol 1, No 1, pp. 47-53, June 2017, DOI: https://doi.org/10.29099/ijair.v1i1.1This paper has been found to be in violation of the International Journal of Artificial Intelligence Research Publication principles and has been retracted.The article contained redundant material, the editor investigated and found that the paper published in JURASIK(Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol. 1, No. 1, pp. 56-63, 2016,  http://ejurnal.tunasbangsa.ac.id/index.php/jurasik/article/view/9The document and its content have been removed from International Journal of Artificial Intelligence Research, and reasonable effort should be made to remove all references to this article.
Implementasi JST pada Prediksi Total Laba Rugi Komprehensif Bank Umum dan Konvensional dengan Backpropagation Windarto, Agus Perdana; Lubis, Muhammad Ridwan; Solikhun, Solikhun
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 5 No 4: Agustus 2018
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (327.882 KB) | DOI: 10.25126/jtiik.201854767

Abstract

Total laba rugi komprehensif merupakan hasil yang digunakan untuk mengukur keberhasilan kinerja perusahaan selama periode tertentu yang tidak dipengaruhi oleh operasi normal perusahaan. Informasi total lapa rugi komprehensif sangat penting bagi beberapa pengguna laporan keuangan seperti investor, kreditor dan manajemen dalam memprediksi dimana posisi angka total laba rugi komprehensif untuk menentukan arah investasi masyarakat ke depan, begitu juga bagi pihak bank berguna untuk menentukan kebijakan strategi pemasaran dalam meninggkatkan total laba komprehensif tersebut. Penelitian ini bertujuan untuk membuat prediksi dengan menggunakan Artificial Intelligence dengan algortima backpropagation. Data yang digunakan bersumber dari Otoritas Jasa Keuangan (OJK) pada PT. Bank Mandiri (Persero) Tbk (Januari-Oktober 2016). Untuk melakukan prediksi dengan algortima backpropagation. Proses dilakukan dengan membagi data pelatihan dan pengujian untuk memperoleh model arsitektur terbaik. model arsitektur pelatihan dan pengujian yang digunakan untuk melakukan prediksi Total laba rugi komprehensif yakni: 4-25-1; 4-50-1; 4-50-75-1 dan 4-100-1. Dari serangkaian uji coba didapat pola terbaik dari arsitektur backpropagation adalah 4-50-1 dengan Means Square Error 0,0009978666, epoch 1977 dan akurasi 80% yang selanjutnya akan digunakan untuk melakukan prediksi. Abstract Total comprehensive income is the result used to measure the success of a company's performance over a certain period that is not affected by the company's normal operations. Total information on comprehensive loss is very important for some financial report users such as investors, creditors and management in predicting where the position of the total comprehensive income statement is to determine the direction of public investment going forward, as well as for banks to determine marketing strategy in increasing total profit comprehensive. This study aims to make predictions using Artificial Intelligence with backpropagation algorithms. The data used is sourced from the Financial Services Authority (OJK) at PT. Bank Mandiri (Persero) Tbk (January-October 2016). To predict with backpropagation algorithm. The process is carried out by dividing training and testing data to obtain the best architectural model. the training and testing architectural model used to predict the total comprehensive income: 4-25-1; 4-50-1; 4-50-75-1 and 4-100-1. From a series of trials obtained the best pattern of backpropagation architecture is 4-50-1 with Means Square Error 0,0009978666, epoch 1977 and accuracy 80% which will then be used to make predictions. 
POLAK-RIBIERE CONJUGATE GRADIENT ALGORITHM IN PREDICTING THE PERCENTAGE OF OPEN UNEMPLOYMENT IN NORTH SUMATRA PROVINCE Amalya, Nanda; Solikhun, Solikhun
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 1 (2024): JUTIF Volume 5, Number 1, February 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.1.1047

Abstract

The economic problem that has a direct impact on human life and welfare is unemployment. One of the cities in Indonesia with the highest unemployment rate is North Sumatra Province. For example, Tebing Tinggi City had the highest unemployment rate of 9.73% in 2017, while Nias Selatan had the lowest percentage of 0.31%. This research is important to do in order to anticipate the unemployment rate in North Sumatra for any party, be it the government or the private sector, so that they can work together to overcome the problem of unemployment in the future which is the main problem in the economy. For example, the government creates programs to help reduce the number of unemployed, provide preparation or do other things, helping people to become more imaginative and have skills so they can compete in the world market. Predicting unemployment has been the subject of many studies, one of which is by utilizing artificial neural networks. This study aims to predict the percentage of unemployed in North Sumatra from 2022 to 2026, using the Backpropagation Neural Network Algorithm, the Conjugate Gradient Polak-Ribiere method and Matlab version 2011 for research and data analysis. This research utilizes open action rate stimulation data for the population of North Sumatra based on residents aged over 15 years from 2017 to 2021. Using five architectural models, namely: 4-50-1, 4-55-1, 4-70- 1, 4-75-1, and 4-77-1. The final results were obtained using the most accurate architectural model, namely model 4-75-1 which has a Mean Squared Error (MSE) of 0.0000004288 and an accuracy rate of 100% with a time of 00.09 at epoch 452.
Relevansi Konsepsi Rahmatan Lil Alamin dengan Keragaman Umat Beragama Solikhun, Solikhun
Hanifiya: Jurnal Studi Agama-Agama Vol. 4 No. 1 (2021): Hanifiya: Jurnal Studi Agama-Agama
Publisher : Program Studi Studi Agama-Agama Pascasarjana UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/hanifiya.v4i1.11487

Abstract

The impression of western world to the eastern has not shown a positive proportion. It always considers the latter as a minor. It is more so after the incident of WTC 9 September 2001. The eastern or as an assertive known as a terrorist, unhuman, and far from humane proportion. While in Islam itself, there is rahmatan li al-‘alamin. These things make the researcher interested in examining deeper what it means to be a rahmatan li al-‘alamin in Koran as a source of that word. Apart from the phrase rahmatan li al-‘alamin, a rahmat word is not connected to the li al-‘alamin word (universe) in the Koran. What also precisely is the difference between grace (rahmat) and rahmatan li al-‘alamin. Indonesia is a plural nation. That is not only ethnic, language, and custom tradition, but also religion. How is the relationship between faith in diversity frame? Is there relevance of li al-‘alamin in the diversity frame of religious people? Some questions need to search for answer in various reverence. The nation's founders have been proud not to obtrude by doing sharia for the adherents is a space for tolerance and religious people.
PERANCANGAN ABSENSI QR CODE MAHASISWA BERBASIS WEBSITE PADA STIKOM TUNAS BANGSA PEMATANG SIANTAR MENGGUNAKAN METODE AGILE Rafai, Muhammad; Solikhun, Solikhun; Safii, M.
Jurnal Manajamen Informatika Jayakarta Vol 4 No 1 (2024): JMI Jayakarta (February 2024) Seleksi Paper SENATIKA-4 (October 2023)
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52362/jmijayakarta.v4i1.1303

Abstract

This research discusses the implementation of a web-based attendance system that utilizes QR scanner technology to record individual attendance, especially in an educational environment. The report also highlights the primary benefits of this approach, such as process efficiency, data accuracy, and real-time information access. The web-based attendance system using QR scanner technology not only enhances administrative effectiveness but also provides a more modern and interactive experience for individuals who need to be accounted for. This helps reduce the risk of errors in manual attendance recording and provides faster and more accurate access to attendance data. In this research, the author used various methods to collect data, including observation and a literature review. The author relied on various online documentation sources as data references for this report. The documents used by the author included several Scopus-indexed journals, e-books, and various digital news pages from the past 5 years. For the development method of this website, the author employed the Agile methodology. Agile is one of the models of the Software Development Life Cycle (SDLC). The results of this research, which combine QR codes and web access, make this attendance system a relevant and innovative solution for efficient attendance management.
Optimisasi VGG16 dengan Transfer Learning dalam Mendeteksi Penyakit Pada Daun Jagung Ht. Barat, Ade Ismiaty Ramadhona; Astuti, Wiwik Sri; Wanto, Anjar; Solikhun, Solikhun
Bulletin of Computer Science Research Vol. 5 No. 5 (2025): August 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i5.631

Abstract

Corn is one of the major agricultural commodities that plays a strategic role in national food security. However, its productivity often declines due to leaf diseases such as Blight, Common Rust, and Gray Leaf Spot. Manual disease detection is considered inefficient and prone to human error, especially on a large scale. This study aims to develop an automated deep learning-based system for accurate classification of corn leaf diseases. The proposed model utilizes the Convolutional Neural Network (CNN) architecture VGG16 with a transfer learning approach. The dataset comprises 1,200 labeled images of corn leaves categorized into four disease classes, obtained from Kaggle. Image augmentation techniques were applied to improve data diversity and enhance model generalization. The performance of VGG16 was compared with VGG16 Baseline architecture and MobileNetV2. Experimental results show that VGG16 with transfer learning achieved the highest classification accuracy of 96.25%, outperforming the baseline VGG16 (92.92%) and MobileNetV2 (84.58%). These findings demonstrate the effectiveness of VGG16-based transfer learning in automating corn leaf disease detection, supporting the implementation of precision agriculture technology.
Comparison of Hyperparameter Tuning Methods for Optimizing K-Nearest Neighbor Performance in Predicting Hypertension Risk Trianda, Dimas; Hartama, Dedy; Solikhun, Solikhun
JURNAL TEKNIK INFORMATIKA Vol. 18 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.42260

Abstract

Hypertension is a major cause of cardiovascular disease, making early risk prediction essential. According to WHO, hypertension cases are estimated to reach 1.28 billion by 2023. This study aims to optimize the K-Nearest Neighbor (KNN) algorithm for predicting hypertension risk through hyperparameter tuning. Three methods Grid SearchCV, Bayes SearchCV, and Random SearchCV are compared to determine the best parameter configuration. The dataset, obtained from Kaggle, consists of 520 balanced samples (260 positive and 260 negative) with 18 health-related features such as age, gender, blood pressure, cholesterol, glucose, and others. After preprocessing, the KNN model is tuned using each method by testing combinations of neighbors (k), weight types, and distance metrics. Results show Bayes SearchCV achieved the highest accuracy of 92%, outperforming the baseline KNN model, which had 85% accuracy. The ROC AUC score of 0.96191 also indicates excellent classification performance. In conclusion, Bayes SearchCV significantly improves KNN's predictive ability in hypertension risk classification.
Refining CNN architecture for forest fire detection: improving accuracy through efficient hyperparameter tuning Kurniawan, Kurniawan; Perdana Windarto, Agus; Solikhun, Solikhun
Bulletin of Electrical Engineering and Informatics Vol 14, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i2.8805

Abstract

Forest fire detection is one of the critical challenges in disaster mitigation and environmental management. This research aims to increase the accuracy of forest fire detection through improving the convolutional neural network (CNN) architecture. The main focus of research is on efficient hyperparameter tuning, which includes selecting and optimizing key parameters in CNN architectures such as convolutional layers, kernel size, number of neurons in hidden layers, and learning algorithms. By utilizing grid search techniques and heuristic-based optimization algorithms, the resulting CNN model shows significant improvements in detection accuracy compared to previous approaches. The evaluation was carried out using a pre-processed forest fire image dataset, and the results show that architectural refinement and appropriate hyperparameter tuning can substantially improve model performance. Evaluation results comparing two models, VGG16 and the proposed method, show significant improvements over the proposed method. The proposed method shows better capabilities with an accuracy of 95.31% and a precision of 97.22%. This research contributes to developing a more reliable and efficient forest fire detection system, which is expected to be used in real applications to reduce the impact of forest fires more effectively.
The Application of the Fletcher-Reeves Algorithm to Predict Spinach Vegetable Production in Sumatra Ardha, Mhd. Zoel; Yasin, Verdi; Solikhun, Solikhun
International Journal of Engineering and Computer Science Applications (IJECSA) Vol. 2 No. 1 (2023): March 2023
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v2i1.2417

Abstract

Determination of spinach plant predictions is one of the most critical decision-making processes. In predicting spinach plants in each period, it depends on each period, both the previous and subsequent periods. The production of spinach plants that change every period causes uncertainty in predicting. The method used to indicate the data is the Fletcher-Reeves algorithm, it is an appropriate development technique compared to the backpropagation strategy because this strategy can speed up the preparation time to arrive at the minimum convergence value. This paper does not discuss the prediction results. Still, it discusses the ability of the Fletcher-Reeves algorithm to make predictions based on the spinach production dataset obtained from the Central Statistics Agency. The purpose of this research is to see the accuracy and performance measurement of the algorithm in the search for the best results to solve the prediction of spinach plants in Sumatra. The research data used are spinach vegetable production data in North Sumatra. Based on this data, a network architecture model will be formed and determined, including 2-20-1, 2-30-1, 2-35-1, 2-45-1, and 2-50-1. After training and testing, these five models show that the best architectural model is 2-20-1 with an MSE value of 0.00608399, the lowest among the other four models. So the model can be used to predict spinach plants in Sumatra.A well-prepared abstract enables the reader to identify the basic content of a document quickly and accurately, to determine its relevance to their interests, and thus to decide whether to read the document in its entirety.